FAFACHR opened a new issue #14663: Error with NDArray.Reshape URL: https://github.com/apache/incubator-mxnet/issues/14663 Thank you for this useful framework, I'm new in this field and I'm trying to work on computer vision stuff so I'm using gluoncv to work on instance segmentation but while I'm doing the training with coco pretrained weights on my own dataset and my own classes. I got an exception : "mxnet.base.MXNetError: [12:00:50] src/ndarray/ndarray.cc:253: Check failed: shape_.Size() == shape.Size() (2007040 vs. 50176) NDArray.Reshape: target shape must have the same size as current shape when recording with autograd " this error is raised by MXNetError. Anyone have a solution ?
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
